Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the operation read-only and idempotent, so the description does not need to repeat safety. It adds valuable behavioral context beyond annotations: the dependency on xref_index.json.gz (with generation command) and the vector-search fallback when the index is not loaded. This tells the agent about data availability and degraded behavior in a way the schema and annotations do not.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences carry all essential information with no filler: the first defines the tool's scope and output categories, the second states the prerequisite and fallback behavior. Information is front-loaded, with the most important purpose statement first.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only cross-reference tool with annotations covering safety, the description is mostly complete: it names the target, the output categories, the prerequisite index, and the fallback. There is no output schema, so some ambiguity about the exact result structure remains, but the description provides enough context for an agent to decide whether and how to invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents methodKey format, depth bounds, categories, and maxResults. The description's list of categories (callers, callees, inheritance, etc.) loosely maps to the categories parameter, but it does not add substantive semantic detail beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource (a class or method) and the verb (build a full cross-reference profile), and enumerates the content: callers, callees, inheritance chain, interface implementations, overrides, attributes. It is distinguishable from siblings like find_references by this explicit scope, though it never names a sibling or states the comparison directly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives important context about when the tool can be used: it requires xref_index.json.gz and falls back to vector-search when XRef is not loaded. However, it does not explicitly state when to prefer this tool over sibling tools such as find_references or find_change_impact, nor does it provide exclusions or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.